Dynamic Transfer for Multi-Source Domain Adaptation

Abstract

Recent works of multi-source domain adaptation focus on learning a domain-agnostic model, of which the parameters are static. However, such a static model is difficult to handle conflicts across multiple domains, and suffers from a performance degradation in both source domains and target domain. In this paper, we present dynamic transfer to address domain conflicts, where the model parameters are adapted to samples. The key insight is that adapting model across domains is achieved via adapting model across samples. Thus, it breaks down source domain barriers and turns multi-source domains into a single-source domain. This also simplifies the alignment between source and target domains, as it only requires the target domain to be aligned with any part of the union of source domains. Furthermore, we find dynamic transfer can be simply modeled by aggregating residual matrices and a static convolution matrix. Experimental results show that, without using domain labels, our dynamic transfer outperforms the state-of-the-art method by more than 3% on the large multi-source domain adaptation datasets -- DomainNet. Source code is at https://github.com/liyunsheng13/DRT.

Accepted by CVPR 2021

References in corpus (9)

• Learning Transferable Features with Deep Adaptation Networks
• VisDA: The Visual Domain Adaptation Challenge
• CondConv: Conditionally Parameterized Convolutions for Efficient Inference
• Dynamic Convolution: Attention over Convolution Kernels
• Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
• Mutual Learning Network for Multi-Source Domain Adaptation
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
• Curriculum Manager for Source Selection in Multi-Source Domain Adaptation
• Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation